biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Reorganize pooling layers (#31973)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-09 19:02:14 +08:00
committed by GitHub
parent 020732800c
commit c8ed39b9dd
34 changed files with 1290 additions and 1143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
vllm/model_executor/models/gpt2.py
View File

@@ -41,6 +41,7 @@ from vllm.model_executor.layers.linear import (
RowParallelLinear,
)
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.pooler import DispatchPooler
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead,
@@ -49,7 +50,6 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.sequence import IntermediateTensors
from ..layers.pooler import DispatchPooler, Pooler
from .interfaces import SupportsCrossEncoding, SupportsPP
from .utils import (
AutoWeightsLoader,
@@ -351,19 +351,7 @@ class GPT2ForSequenceClassification(nn.Module, SupportsCrossEncoding):
pooler_config = vllm_config.model_config.pooler_config
assert pooler_config is not None
self.pooler = DispatchPooler(
{
"token_classify": Pooler.for_token_classify(
pooler_config, classifier=self.score
),
"classify": Pooler.for_classify(
pooler_config, classifier=self.score, act_fn="classify"
),
"score": Pooler.for_classify(
pooler_config, classifier=self.score, act_fn="score"
),
}
)
self.pooler = DispatchPooler.for_seq_cls(pooler_config, classifier=self.score)
def embed_input_ids(self, input_ids: torch.Tensor) -> torch.Tensor:
return self.transformer.embed_input_ids(input_ids)